Automated Algorithm Selection in Single-Objective Continuous Optimization: A Comparative Study of Deep Learning and Landscape Analysis Methods
Prager, Raphael Patrick; Seiler, Moritz Vinzent; Trautmann, Heike; Kerschke, Pascal
Zusammenfassung
In recent years, feature-based automated algorithm selection using exploratory landscape analysis has demonstrated its great potential in single-objective continuous black-box optimization. However, feature computation is problem-specific and can be costly in terms of computational resources. This paper investigates feature-free approaches that rely on state-of-the-art deep learning techniques operating on either images or point clouds. We show that point-cloud-based strategies, in particular, are highly competitive and also substantially reduce the size of the required solver portfolio. Moreover, we highlight the effect and importance of cost-sensitive learning in automated algorithm selection models.
Schlüsselwörter
Automated Algorithm Selection; Exploratory Landscape Analysis; Deep Learning; Continuous Optimization
Zitieren als
Prager, R. P., Seiler, M. V., Trautmann, H., & Kerschke, P. (2022). Automated Algorithm Selection in Single-Objective Continuous Optimization: A Comparative Study of Deep Learning and Landscape Analysis Methods. In Rudolph, G., Kononova, A. V., Aguirre, H., Kerschke, P., Ochoa, G., & Tušar, T. (Eds.),
Parallel Problem Solving from Nature — PPSN XVII (pp. 3–17). Cham: Springer International Publishing.
Details
Publikationstyp
Forschungsartikel in Sammelband (Konferenz)
Begutachtet
Ja
Publikationsstatus
Veröffentlicht
Jahr
2022
Konferenz
International Conference on Parallel Problem Solving from Nature
Konferenzort
Dortmund
Buchtitel
Parallel Problem Solving from Nature -- PPSN XVII
Herausgeber
Rudolph, Günter; Kononova, Anna V.; Aguirre, Hernán; Kerschke, Pascal; Ochoa, Gabriela; Tušar, Tea
Erste Seite
3
Letzte Seite
17
Verlag
Springer International Publishing
Ort
Cham
Sprache
Englisch
ISBN
978-3-031-14714-2
DOI
Gesamter Text
